344
Productivity & Workflow355
Automation & Workflow225
Software Development251
Marketing & Growth193
AI Infrastructure & MLOps175
Writing & Content Creation204
Data & Analytics142
Photography & Imaging156
Design & Creative170
Customer Support133
Sales & Outreach125
Voice & Speech135
Education & Learning131
Operations & Admin87
OpenAI updated Codex with reusable cloud workspaces, voice controls in its command line tool, new code review features, and new security scanning tools.
In short: OpenAI updated Codex so developers can reuse the same cloud workspace across devices, and it also added new tools for voice control, code review, and security checks.
OpenAI announced new features for Codex at its Dev Day event. Codex is OpenAI’s software helper that can write and edit code.
The biggest change is reusable cloud development environments. A “cloud environment” is like a ready-to-use work computer that lives on the internet instead of on your laptop. OpenAI says developers can now keep these environments around, set them up the way they want, and open them from different devices, including a phone.
OpenAI also refreshed Codex CLI, which is Codex’s command line tool (a text based way to control software, like typing instructions instead of clicking buttons). The update adds voice controls, plus a new view to track multiple Codex tasks at once.
Codex is also getting a new code review experience inside the ChatGPT desktop app. This lets users see summaries of code changes and ask Codex about possible problems before leaving feedback on GitHub or GitLab.
On the security side, OpenAI introduced Codex Security Cloud. It can scan a whole code repository (a project’s main folder and history, like a shared filing cabinet for code) on a schedule or when new changes are added. OpenAI says Codex can also group repeated alerts and prepare fixes in the cloud, even while a developer is away.
For teams building software, these updates aim to reduce setup time and make work easier to continue from anywhere. The security scanning also reflects a growing push to catch problems earlier, before they turn into real-world data or system issues.
Source: TechCrunch AI